Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations indicating a mutating operation, the description discloses important side effects: it removes both the database record and any attached file. It also reveals the freeze condition after goal close, which is critical behavioral context not available from the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with no filler. The primary action is front-loaded, followed by the most important precondition and the side-effect of file removal. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter delete tool, the description is complete: it states the action, the target identifier, the key precondition, and the full scope of what gets removed. The annotations already cover mutability and idempotency, so nothing critical is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents the evidenceId parameter as a UUID. The description reinforces that deletion is by UUID but does not add new parameter-level details beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb and resource: 'Delete an evidence record by UUID.' This clearly identifies the operation and the object it acts on, and distinguishes it from sibling tools that remove notes, assumptions, or criteria.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when deletion is allowed and explicitly states a key exclusion: it is forbidden when the owning goal is already done. It does not name alternative tools, but the operation is specific enough that the main usage intent is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.